CN110782627A - Anti-lost system based on multi-person face recognition - Google Patents
Anti-lost system based on multi-person face recognition Download PDFInfo
- Publication number
- CN110782627A CN110782627A CN201910899946.9A CN201910899946A CN110782627A CN 110782627 A CN110782627 A CN 110782627A CN 201910899946 A CN201910899946 A CN 201910899946A CN 110782627 A CN110782627 A CN 110782627A
- Authority
- CN
- China
- Prior art keywords
- module
- face
- face recognition
- early warning
- processing module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0476—Cameras to detect unsafe condition, e.g. video cameras
Abstract
The invention provides a multi-person face recognition-based anti-lost system which comprises an acquisition module, a monitoring module, a processing module, an early warning module and a cloud module. The processing module is a core module and also comprises a face detection sub-module and a face recognition and decision sub-module. The invention designs a novel anti-lost system based on family grouping by utilizing the prior advanced face detection and face recognition technology. The system can be deployed in places with frequent lost accidents such as districts and shopping malls, and once the persons without the behavior ability such as children and the old people are monitored that no legal guardian accompanies the persons to leave a designated safety area, the guardian and the security personnel nearby can be immediately reminded. Compared with the existing security monitoring system, the invention can quickly respond to the occurrence of accidents and automatically early warn, thereby greatly improving the safety and the working efficiency of the security system.
Description
Technical Field
The invention belongs to the technical field of security monitoring electronic systems, and particularly relates to a multi-person face recognition-based anti-lost system.
Background
As the mobile migration of our country is becoming active, the number of lost and scattered people is increasing every year. It is reported that about 1300 old people are lost due to lost, mental disease, senile dementia and other reasons in China on average every day, and more than ten thousand children are lost due to going to be sold, going out of home and lost every year. Due to the reasons that the current lost retrieval system in China is not perfect enough, the accident reporting is not timely, the police force is limited, the retrieval rate of tens of thousands of lost people per year is less than 10%, and countless families are separated and broken due to the loss of relatives. With the continuous maturity of artificial intelligence technique, the technical scheme that relies on face recognition technology to solve children, the old man problem of wandering away constantly emerges, has promoted to a certain extent and has retrieved efficiency. However, these recovery schemes usually take actions after the early warning information is issued immediately after the accident occurs, and the people often miss the gold rescue time.
Disclosure of Invention
The invention aims to solve the technical problems of the existing security system, and provides a multi-person face recognition-based anti-lost system which can automatically judge, quickly react and early warn efficiently to accidents, so as to solve the technical defects.
A system for preventing people from being lost based on multi-person face recognition comprises an acquisition module 1, a monitoring module 2, a processing module 3, an early warning module 4 and a cloud module 5;
the acquisition module 1 is used for user registration and storing registration information into a server in the processing module 3;
the monitoring module 2 is used for shooting the video image of the monitored area in real time and uploading the real-time video image to a server in the processing module 3;
the processing module 3 is used for carrying out face detection on the video image transmitted by the monitoring module 2, comparing the detected face with the registered user and finally generating an early warning decision;
the early warning module 4 is used for implementing early warning operation on the early warning decision generated by the processing module 3;
the cloud module 5 is used for updating the latest face recognition algorithm model in the processing module 3 or directly performing face recognition by using a cloud server if the network condition allows.
Further, the registration information of the target user in the acquisition module 1 includes image information and text information, wherein the image information includes a plurality of recent head images of the target user and a target user guardian, and the images are shot at different angles; the text information comprises basic information of the target user and basic information of the guardian of the target user.
Further, the monitoring module 2 adopts a network high-definition panoramic monitoring camera for monitoring.
Further, the processing module 3 includes a face detection sub-module and a face recognition and decision sub-module.
Further, the face detection sub-module comprises a face detection technology and a face registration technology, wherein the face detection technology can locate all the faces appearing in the video image; the face registration technology is used for picking out the appeared face region and scaling the face region to a fixed size, and then face alignment and illumination correction are carried out.
Further, the face recognition and decision sub-module recognizes whether a target user exists in the video image by using a face recognition technology, if the target user exists, whether a guardian exists in the video image in the latest time is searched, and if the guardian does not exist, the early warning module 4 is triggered.
Further, after the early warning module 4 is triggered, nearby security personnel and guardians can be contacted to determine whether an accident occurs, and the processing module 3 transmits the accident monitoring video image to the security personnel.
Compared with the prior art, the invention has the advantages that:
1. the invention collects the target person and the appointed guardian by taking a group as a unit through the collection module. In addition to requiring registration information of the target user himself, registration information of one or more guardians of the target user is also required, thus constituting a group. The registration information contains member basic character information and head portrait photos of different angles. The registering mode can bind the disabled person and the guardian into a group, and if the disabled person and the guardian cannot be identified at the same time, the early warning is quickly carried out, and the registered guardian is informed of the situation in time.
2. The invention uses a high-definition camera to monitor a designated area in real time and transmit a monitoring video image to a server of a processing module, detects whether a registered target user exists in the video image or not through a face recognition technology, if the registered target user exists, whether a guardian simultaneously exists in the video image or not is searched in the latest time, and if the guardian does not exist, an early warning module is triggered. The safety protection early warning mechanism overcomes the defects of untimely accident response and inconvenient management of the traditional safety protection system, and can realize automatic quick response of accident occurrence.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
fig. 1 is an architecture diagram of an anti-lost system based on face recognition of multiple persons according to the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
A system for preventing people from being lost based on face recognition of multiple people is shown in figure 1 and comprises an acquisition module 1, a monitoring module 2, a processing module 3, an early warning module 4 and a cloud module 5. The network devices involved in all the modules are connected through a local area network, wherein the devices in the early warning module 4 and the cloud module 5 need to be connected with the internet.
In this embodiment, the acquisition module 1 specifically includes a network high-definition camera and a registration website, and is mainly used for performing online code scanning registration by a target user with a family group as a unit. In addition to requiring registration information of the target user himself, registration information of one or more guardians of the target user is also required, thereby constituting a family group. The registration information comprises member basic character information (such as name, age, family address, contact information and the like) and recent head portrait photos from different angles, and the head portrait photos can be uploaded or shot on site. All the registration information is stored in a server in the processing module (3) through a local area network.
In this embodiment, the monitoring module 2 specifically includes a plurality of network high-definition panoramic cameras, is deployed in key areas such as a cell gate, a mall entrance and exit, and is mainly used for shooting the video images of the monitoring area in real time, and uploading the real-time video images to the server in the processing module 3 through the local area network.
In this embodiment, the processing module 3 specifically includes a server equipped with 4 GPU graphics cards of Tesla K80, and the server operating system is Ubuntu 16.04 and is configured with a Python 3.6 operating environment and a Mysql 14.14 database. A core Python program for face detection, face recognition and early warning decision is deployed in the server and comprises a face detection submodule and a face recognition and decision submodule. The face detection sub-module comprises a face detection algorithm and a face registration algorithm, and the face detection algorithm can position all faces appearing in the video image; the face registration algorithm extracts the face region and scales the face region to a fixed size, and then face alignment and illumination correction are performed. The face recognition and decision sub-module identifies whether a target user exists in the video image by comparing the head image library in the registration information and using a face recognition algorithm, if the target user exists, whether a registered guardian of the user exists in the video image within the last 5 seconds is searched, and if the guardian does not exist, the early warning module 4 is automatically triggered.
In this embodiment, the early warning module 4 is configured to perform an early warning operation on the early warning decision generated by the processing module 3, specifically, contact a nearby security worker and notify a guardian by using an internet phone.
In this embodiment, the cloud module 5 is an optional module, and is configured to update the latest face recognition algorithm model in the processing module 3 or directly perform face recognition by using a cloud server when a network condition allows.
The invention is deployed in key areas with frequent loss accidents, such as residential districts, shopping malls and the like, can automatically early warn and quickly react to the loss accidents, and greatly improves the safety and the working efficiency of the security system.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (7)
1. A multi-person face recognition-based anti-lost system is characterized by comprising an acquisition module (1), a monitoring module (2), a processing module (3), an early warning module (4) and a cloud module (5);
the acquisition module (1) is used for registering a user and storing registration information into a server in the processing module (3);
the monitoring module (2) is used for shooting a video image of a monitored area in real time and uploading the real-time video image to a server in the processing module (3);
the processing module (3) is used for carrying out face detection on the video image transmitted by the monitoring module (2), comparing the detected face with the registered user and finally generating an early warning decision;
the early warning module (4) is used for implementing early warning operation on the early warning decision generated by the processing module (3);
the cloud module (5) is used for updating the latest face recognition algorithm model in the processing module (3) or directly performing face recognition by using a cloud server under the condition that network conditions allow.
2. The system for preventing the loss of the face of the multiple persons based on the face recognition of the multiple persons as claimed in claim 1, wherein the registration information of the target user in the acquisition module (1) comprises image information and character information, wherein the image information comprises multiple recent head images of the target user and a guardian of the target user, and the images are shot through different angles; the text information comprises basic information of the target user and basic information of the guardian of the target user.
3. The system for preventing the loss of people based on the face recognition of multiple people as claimed in claim 1, wherein the monitoring module (2) adopts a network high-definition panoramic monitoring camera for monitoring.
4. The system of claim 1, wherein the processing module (3) comprises a face detection sub-module and a face recognition and decision sub-module.
5. The system of claim 4, wherein the face detection sub-module comprises face detection technology and face registration technology, wherein the face detection technology can locate all faces appearing in the video image; the face registration technology is used for picking out the appeared face region and scaling the face region to a fixed size, and then face alignment and illumination correction are carried out.
6. The system of claim 4, wherein the face recognition and decision sub-module uses face recognition technology to identify whether a target user exists in the video image, if so, the sub-module searches whether a guardian exists in the video image in the latest time, and if not, the sub-module triggers the early warning module (4).
7. The system for preventing the loss of people based on the face recognition of multiple people as claimed in claim 1, wherein after the early warning module (4) is triggered, the system can contact the security personnel and guardians nearby to confirm whether an accident occurs, and the processing module (3) transmits the accident monitoring video image to the security personnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910899946.9A CN110782627A (en) | 2019-09-23 | 2019-09-23 | Anti-lost system based on multi-person face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910899946.9A CN110782627A (en) | 2019-09-23 | 2019-09-23 | Anti-lost system based on multi-person face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110782627A true CN110782627A (en) | 2020-02-11 |
Family
ID=69383760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910899946.9A Pending CN110782627A (en) | 2019-09-23 | 2019-09-23 | Anti-lost system based on multi-person face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110782627A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111292502A (en) * | 2020-02-17 | 2020-06-16 | 浙江大华技术股份有限公司 | Method and device for preventing early warning of lost and storage medium |
| CN113689661A (en) * | 2020-05-19 | 2021-11-23 | 深圳市中兴系统集成技术有限公司 | Hooking child behavior early warning system based on video analysis |
| CN113852740A (en) * | 2021-09-18 | 2021-12-28 | 广东睿住智能科技有限公司 | Anti-lost system and method and readable storage medium thereof |
| CN113963524A (en) * | 2021-10-26 | 2022-01-21 | 云知声智能科技股份有限公司 | Method and device for identifying strangers in park, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106340093A (en) * | 2016-08-24 | 2017-01-18 | 上海斐讯数据通信技术有限公司 | Security protection method and system for kindergarten pick-up |
| CN107169461A (en) * | 2017-05-19 | 2017-09-15 | 苏州寅初信息科技有限公司 | A kind of intelligent and safe method for tracing and its system for market |
| CN107239744A (en) * | 2017-05-15 | 2017-10-10 | 深圳奥比中光科技有限公司 | Monitoring method, system and the storage device of human body incidence relation |
| KR20180090575A (en) * | 2017-02-03 | 2018-08-13 | 박창식 | Illegal passengers detection system |
-
2019
- 2019-09-23 CN CN201910899946.9A patent/CN110782627A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106340093A (en) * | 2016-08-24 | 2017-01-18 | 上海斐讯数据通信技术有限公司 | Security protection method and system for kindergarten pick-up |
| KR20180090575A (en) * | 2017-02-03 | 2018-08-13 | 박창식 | Illegal passengers detection system |
| CN107239744A (en) * | 2017-05-15 | 2017-10-10 | 深圳奥比中光科技有限公司 | Monitoring method, system and the storage device of human body incidence relation |
| CN107169461A (en) * | 2017-05-19 | 2017-09-15 | 苏州寅初信息科技有限公司 | A kind of intelligent and safe method for tracing and its system for market |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111292502A (en) * | 2020-02-17 | 2020-06-16 | 浙江大华技术股份有限公司 | Method and device for preventing early warning of lost and storage medium |
| CN113689661A (en) * | 2020-05-19 | 2021-11-23 | 深圳市中兴系统集成技术有限公司 | Hooking child behavior early warning system based on video analysis |
| CN113852740A (en) * | 2021-09-18 | 2021-12-28 | 广东睿住智能科技有限公司 | Anti-lost system and method and readable storage medium thereof |
| CN113963524A (en) * | 2021-10-26 | 2022-01-21 | 云知声智能科技股份有限公司 | Method and device for identifying strangers in park, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110782627A (en) | Anti-lost system based on multi-person face recognition | |
| JP6905850B2 (en) | Image processing system, imaging device, learning model creation method, information processing device | |
| CN106341661B (en) | Patrol robot | |
| CN108446669B (en) | Motion recognition method, motion recognition device and storage medium | |
| JP6854881B2 (en) | Face image matching system and face image search system | |
| WO2019024414A1 (en) | Method to prevent getting lost and terminal device | |
| CN111325954B (en) | Personnel loss early warning method, device, system and server | |
| CN209543514U (en) | Monitoring and alarm system based on recognition of face | |
| JP2010272958A (en) | Monitoring device, monitoring system, and monitoring program | |
| JP2007272488A (en) | Image processor, monitor camera and image monitoring system | |
| WO2021223665A1 (en) | Method and device for reducing invalid warnings | |
| CN109543607A (en) | Object abnormal state detection method, system, monitor system and storage medium | |
| US10490046B2 (en) | Methods and systems for detecting shoplifting at a retail facility | |
| US11450186B2 (en) | Person monitoring system and person monitoring method | |
| CN111553305B (en) | System and method for identifying illegal videos | |
| JP2014067383A (en) | Behavior monitoring notification system | |
| JP5202419B2 (en) | Security system and security method | |
| JP2011145839A (en) | Monitoring system, device, method and program | |
| CN106611478A (en) | Kindergarten pickup system based on face recognition technology | |
| CN113314230A (en) | Intelligent epidemic prevention method, device, equipment and storage medium based on big data | |
| CN106611454A (en) | Kindergarten sending and picking up system based on palm vein recognition technology | |
| CN115761564A (en) | Follower list processing method, abnormal travel event detection method and system | |
| CN115410113A (en) | Fall detection method and device based on computer vision and storage medium | |
| KR20030040434A (en) | Vision based method and apparatus for detecting an event requiring assistance or documentation | |
| CN106611395A (en) | Kindergarten shuttle system based on iris recognition technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200211 |
|
| RJ01 | Rejection of invention patent application after publication |